Upload folder using huggingface_hub

README.md

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+model-index:
+- name: mistral-finetuned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mistral-finetuned
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the treino_pt_rde dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726c6d74dca50d92242de5222e2b5fc378023efa426fb5b20269d458d4c24021
+size 83945296

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 2.2441603085736346e+17,
+    "train_loss": 0.04925085334428426,
+    "train_runtime": 13305.7708,
+    "train_samples_per_second": 0.838,
+    "train_steps_per_second": 0.026
+}

checkpoint-348/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-348/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-348/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726c6d74dca50d92242de5222e2b5fc378023efa426fb5b20269d458d4c24021
+size 83945296

checkpoint-348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ec811984e978fd3fcf6f1d1df1c55ff9efc3d103e3f1a1453c1e260b537fcc
+size 168149074

checkpoint-348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-348/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0282d00eed9fe2ab27061734672e5936a63ea9e59fda708608ae904fc55aa57
+size 1064

checkpoint-348/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-348/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-348/trainer_state.json

@@ -0,0 +1,271 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9935483870967743,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 1.3349374532699585,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.1805,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 1.0496348142623901,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.0827,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 1.1902973651885986,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.0722,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.8137356638908386,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0637,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.8646667003631592,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0646,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 1.2397544384002686,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0619,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.8160271048545837,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0588,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.8985416293144226,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.0594,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.968460738658905,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.059,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.7749939560890198,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0557,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.6407869458198547,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0493,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 1.2854279279708862,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0509,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.60258948802948,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0419,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.9239497780799866,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.042,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.7352257966995239,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0432,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.8709537386894226,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0475,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.7810623049736023,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0448,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.6514085531234741,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0407,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.8177109956741333,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0421,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.9916985630989075,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0401,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 1.0323394536972046,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0438,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.920881450176239,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0444,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 1.1360812187194824,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.041,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.8304557800292969,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0317,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.8478759527206421,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0357,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 1.0847315788269043,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0386,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.6213060617446899,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0289,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 1.0422612428665161,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0307,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 0.9629487991333008,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0338,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.7275118827819824,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0279,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9140329360961914,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0321,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 1.0714858770370483,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0352,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.843151330947876,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0341,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.6754664182662964,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0315,
+      "step": 340
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2441603085736346e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-348/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6b5e03ab55c7eca1bec1843792810a25ab68a79d546ce327c2c6fad1fe4ce0
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: unsloth
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-Instruct-v0.3
+top.quantization_bit: '4'
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: alpaca
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 8
+train.compute_type: fp16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- treino_pt_rde
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 4
+train.learning_rate: 3e-5
+train.logging_steps: 10
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '3716'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 1000
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,503 @@
+[WARNING|2024-11-25 18:35:33] logging.py:162 >> We recommend enable `upcast_layernorm` in quantized training.
+
+[INFO|2024-11-25 18:35:33] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.float16
+
+[INFO|2024-11-25 18:35:33] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-25 18:35:33] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:35:35] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2024-11-25 18:35:35] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2024-11-25 18:35:35] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-25 18:35:35] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2024-11-25 18:35:35] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2024-11-25 18:35:36] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-25 18:35:36] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:35:36] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2024-11-25 18:35:36] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2024-11-25 18:35:36] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-25 18:35:36] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2024-11-25 18:35:36] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2024-11-25 18:35:36] logging.py:157 >> Add pad token: </s>
+
+[INFO|2024-11-25 18:35:36] logging.py:157 >> Loading dataset treino_pt_rde.json...
+
+[INFO|2024-11-25 18:35:50] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-25 18:35:50] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:35:50] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.
+
+[INFO|2024-11-25 18:35:55] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2024-11-25 18:35:55] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:35:56] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unslothai--colab/snapshots/20f9daee9da18936efa03ad4e1361884c60cca0c/config.json
+
+[INFO|2024-11-25 18:35:57] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unslothai--repeat/snapshots/7c48478c02f84ed89f149b0815cc0216ee831fb0/config.json
+
+[INFO|2024-11-25 18:35:57] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unslothai--vram-16/snapshots/9703344699da71a2bb9f17e575eb918c8f6cb349/config.json
+
+[INFO|2024-11-25 18:35:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unslothai--1/snapshots/7ec782b7604cd9ea0781c23a4270f031650f5617/config.json
+
+[INFO|2024-11-25 18:35:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2024-11-25 18:35:58] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:35:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2024-11-25 18:35:58] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 18:37:37] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/model.safetensors
+
+[INFO|2024-11-25 18:37:37] modeling_utils.py:1670 >> Instantiating MistralForCausalLM model under default dtype torch.float16.
+
+[INFO|2024-11-25 18:37:37] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 770
+}
+
+
+[INFO|2024-11-25 18:38:02] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2024-11-25 18:38:02] modeling_utils.py:4808 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at unsloth/mistral-7b-instruct-v0.3-bnb-4bit.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
+
+[INFO|2024-11-25 18:38:02] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/generation_config.json
+
+[INFO|2024-11-25 18:38:02] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 770
+}
+
+
+[INFO|2024-11-25 18:38:06] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2024-11-25 18:38:06] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2024-11-25 18:38:06] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2024-11-25 18:38:06] logging.py:157 >> Found linear modules: gate_proj,up_proj,v_proj,down_proj,o_proj,q_proj,k_proj
+
+[WARNING|2024-11-25 18:38:10] logging.py:168 >> Unsloth 2024.11.9 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.
+
+[INFO|2024-11-25 18:38:12] logging.py:157 >> trainable params: 20,971,520 || all params: 7,268,995,072 || trainable%: 0.2885
+
+[INFO|2024-11-25 18:38:12] trainer.py:698 >> Using auto half precision backend
+
+[WARNING|2024-11-25 18:38:13] <string>:208 >> ==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
+   \\   /|    Num examples = 3,716 | Num Epochs = 3
+O^O/ \_/ \    Batch size per device = 8 | Gradient Accumulation steps = 4
+\        /    Total batch size = 32 | Total steps = 348
+ "-____-"     Number of trainable parameters = 20,971,520
+
+[INFO|2024-11-25 18:44:44] logging.py:157 >> {'loss': 0.1805, 'learning_rate': 2.9939e-05, 'epoch': 0.09}
+
+[INFO|2024-11-25 18:51:07] logging.py:157 >> {'loss': 0.0827, 'learning_rate': 2.9756e-05, 'epoch': 0.17}
+
+[INFO|2024-11-25 18:57:27] logging.py:157 >> {'loss': 0.0722, 'learning_rate': 2.9453e-05, 'epoch': 0.26}
+
+[INFO|2024-11-25 19:03:51] logging.py:157 >> {'loss': 0.0637, 'learning_rate': 2.9033e-05, 'epoch': 0.34}
+
+[INFO|2024-11-25 19:10:09] logging.py:157 >> {'loss': 0.0646, 'learning_rate': 2.8498e-05, 'epoch': 0.43}
+
+[INFO|2024-11-25 19:16:32] logging.py:157 >> {'loss': 0.0619, 'learning_rate': 2.7853e-05, 'epoch': 0.52}
+
+[INFO|2024-11-25 19:22:55] logging.py:157 >> {'loss': 0.0588, 'learning_rate': 2.7103e-05, 'epoch': 0.60}
+
+[INFO|2024-11-25 19:29:16] logging.py:157 >> {'loss': 0.0594, 'learning_rate': 2.6255e-05, 'epoch': 0.69}
+
+[INFO|2024-11-25 19:35:47] logging.py:157 >> {'loss': 0.0590, 'learning_rate': 2.5315e-05, 'epoch': 0.77}
+
+[INFO|2024-11-25 19:42:12] logging.py:157 >> {'loss': 0.0557, 'learning_rate': 2.4292e-05, 'epoch': 0.86}
+
+[INFO|2024-11-25 19:48:30] logging.py:157 >> {'loss': 0.0493, 'learning_rate': 2.3192e-05, 'epoch': 0.95}
+
+[INFO|2024-11-25 19:54:47] logging.py:157 >> {'loss': 0.0509, 'learning_rate': 2.2026e-05, 'epoch': 1.03}
+
+[INFO|2024-11-25 20:01:14] logging.py:157 >> {'loss': 0.0419, 'learning_rate': 2.0803e-05, 'epoch': 1.12}
+
+[INFO|2024-11-25 20:07:39] logging.py:157 >> {'loss': 0.0420, 'learning_rate': 1.9532e-05, 'epoch': 1.20}
+
+[INFO|2024-11-25 20:13:57] logging.py:157 >> {'loss': 0.0432, 'learning_rate': 1.8225e-05, 'epoch': 1.29}
+
+[INFO|2024-11-25 20:20:19] logging.py:157 >> {'loss': 0.0475, 'learning_rate': 1.6891e-05, 'epoch': 1.38}
+
+[INFO|2024-11-25 20:26:41] logging.py:157 >> {'loss': 0.0448, 'learning_rate': 1.5542e-05, 'epoch': 1.46}
+
+[INFO|2024-11-25 20:33:05] logging.py:157 >> {'loss': 0.0407, 'learning_rate': 1.4188e-05, 'epoch': 1.55}
+
+[INFO|2024-11-25 20:39:22] logging.py:157 >> {'loss': 0.0421, 'learning_rate': 1.2841e-05, 'epoch': 1.63}
+
+[INFO|2024-11-25 20:45:43] logging.py:157 >> {'loss': 0.0401, 'learning_rate': 1.1511e-05, 'epoch': 1.72}
+
+[INFO|2024-11-25 20:52:07] logging.py:157 >> {'loss': 0.0438, 'learning_rate': 1.0210e-05, 'epoch': 1.81}
+
+[INFO|2024-11-25 20:58:30] logging.py:157 >> {'loss': 0.0444, 'learning_rate': 8.9485e-06, 'epoch': 1.89}
+
+[INFO|2024-11-25 21:04:51] logging.py:157 >> {'loss': 0.0410, 'learning_rate': 7.7358e-06, 'epoch': 1.98}
+
+[INFO|2024-11-25 21:11:09] logging.py:157 >> {'loss': 0.0317, 'learning_rate': 6.5822e-06, 'epoch': 2.06}
+
+[INFO|2024-11-25 21:17:32] logging.py:157 >> {'loss': 0.0357, 'learning_rate': 5.4972e-06, 'epoch': 2.15}
+
+[INFO|2024-11-25 21:23:59] logging.py:157 >> {'loss': 0.0386, 'learning_rate': 4.4896e-06, 'epoch': 2.24}
+
+[INFO|2024-11-25 21:30:17] logging.py:157 >> {'loss': 0.0289, 'learning_rate': 3.5676e-06, 'epoch': 2.32}
+
+[INFO|2024-11-25 21:36:49] logging.py:157 >> {'loss': 0.0307, 'learning_rate': 2.7387e-06, 'epoch': 2.41}
+
+[INFO|2024-11-25 21:43:08] logging.py:157 >> {'loss': 0.0338, 'learning_rate': 2.0096e-06, 'epoch': 2.49}
+
+[INFO|2024-11-25 21:49:30] logging.py:157 >> {'loss': 0.0279, 'learning_rate': 1.3864e-06, 'epoch': 2.58}
+
+[INFO|2024-11-25 21:55:50] logging.py:157 >> {'loss': 0.0321, 'learning_rate': 8.7399e-07, 'epoch': 2.67}
+
+[INFO|2024-11-25 22:02:10] logging.py:157 >> {'loss': 0.0352, 'learning_rate': 4.7666e-07, 'epoch': 2.75}
+
+[INFO|2024-11-25 22:08:34] logging.py:157 >> {'loss': 0.0341, 'learning_rate': 1.9760e-07, 'epoch': 2.84}
+
+[INFO|2024-11-25 22:14:53] logging.py:157 >> {'loss': 0.0315, 'learning_rate': 3.9102e-08, 'epoch': 2.92}
+
+[INFO|2024-11-25 22:19:59] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/mistral-finetuned/checkpoint-348
+
+[INFO|2024-11-25 22:19:59] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2024-11-25 22:19:59] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-25 22:20:00] <string>:484 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2024-11-25 22:20:00] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/mistral-finetuned
+
+[INFO|2024-11-25 22:20:00] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2024-11-25 22:20:00] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[WARNING|2024-11-25 22:20:05] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2024-11-25 22:20:05] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2024-11-25 22:20:05] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 2.2441603085736346e+17,
+    "train_loss": 0.04925085334428426,
+    "train_runtime": 13305.7708,
+    "train_samples_per_second": 0.838,
+    "train_steps_per_second": 0.026
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 10, "total_steps": 348, "loss": 0.1805, "lr": 2.9938918800982563e-05, "epoch": 0.08602150537634409, "percentage": 2.87, "elapsed_time": "0:06:29", "remaining_time": "3:39:39"}
+{"current_steps": 20, "total_steps": 348, "loss": 0.0827, "lr": 2.975617265898004e-05, "epoch": 0.17204301075268819, "percentage": 5.75, "elapsed_time": "0:12:52", "remaining_time": "3:31:15"}
+{"current_steps": 30, "total_steps": 348, "loss": 0.0722, "lr": 2.9453249887788343e-05, "epoch": 0.25806451612903225, "percentage": 8.62, "elapsed_time": "0:19:12", "remaining_time": "3:23:37"}
+{"current_steps": 40, "total_steps": 348, "loss": 0.0637, "lr": 2.9032617538884018e-05, "epoch": 0.34408602150537637, "percentage": 11.49, "elapsed_time": "0:25:36", "remaining_time": "3:17:13"}
+{"current_steps": 50, "total_steps": 348, "loss": 0.0646, "lr": 2.84977013093626e-05, "epoch": 0.43010752688172044, "percentage": 14.37, "elapsed_time": "0:31:55", "remaining_time": "3:10:15"}
+{"current_steps": 60, "total_steps": 348, "loss": 0.0619, "lr": 2.7852857642513838e-05, "epoch": 0.5161290322580645, "percentage": 17.24, "elapsed_time": "0:38:18", "remaining_time": "3:03:51"}
+{"current_steps": 70, "total_steps": 348, "loss": 0.0588, "lr": 2.7103338248251055e-05, "epoch": 0.6021505376344086, "percentage": 20.11, "elapsed_time": "0:44:40", "remaining_time": "2:57:26"}
+{"current_steps": 80, "total_steps": 348, "loss": 0.0594, "lr": 2.6255247332346036e-05, "epoch": 0.6881720430107527, "percentage": 22.99, "elapsed_time": "0:51:02", "remaining_time": "2:50:58"}
+{"current_steps": 90, "total_steps": 348, "loss": 0.059, "lr": 2.531549188280135e-05, "epoch": 0.7741935483870968, "percentage": 25.86, "elapsed_time": "0:57:32", "remaining_time": "2:44:56"}
+{"current_steps": 100, "total_steps": 348, "loss": 0.0557, "lr": 2.4291725418235848e-05, "epoch": 0.8602150537634409, "percentage": 28.74, "elapsed_time": "1:03:58", "remaining_time": "2:38:38"}
+{"current_steps": 110, "total_steps": 348, "loss": 0.0493, "lr": 2.3192285656405456e-05, "epoch": 0.946236559139785, "percentage": 31.61, "elapsed_time": "1:10:15", "remaining_time": "2:32:00"}
+{"current_steps": 120, "total_steps": 348, "loss": 0.0509, "lr": 2.2026126610496852e-05, "epoch": 1.032258064516129, "percentage": 34.48, "elapsed_time": "1:16:32", "remaining_time": "2:25:26"}
+{"current_steps": 130, "total_steps": 348, "loss": 0.0419, "lr": 2.0802745666212592e-05, "epoch": 1.118279569892473, "percentage": 37.36, "elapsed_time": "1:23:00", "remaining_time": "2:19:11"}
+{"current_steps": 140, "total_steps": 348, "loss": 0.042, "lr": 1.953210623354359e-05, "epoch": 1.2043010752688172, "percentage": 40.23, "elapsed_time": "1:29:25", "remaining_time": "2:12:50"}
+{"current_steps": 150, "total_steps": 348, "loss": 0.0432, "lr": 1.8224556603165363e-05, "epoch": 1.2903225806451613, "percentage": 43.1, "elapsed_time": "1:35:43", "remaining_time": "2:06:21"}
+{"current_steps": 160, "total_steps": 348, "loss": 0.0475, "lr": 1.689074566830434e-05, "epoch": 1.3763440860215055, "percentage": 45.98, "elapsed_time": "1:42:04", "remaining_time": "1:59:56"}
+{"current_steps": 170, "total_steps": 348, "loss": 0.0448, "lr": 1.5541536198449044e-05, "epoch": 1.4623655913978495, "percentage": 48.85, "elapsed_time": "1:48:27", "remaining_time": "1:53:33"}
+{"current_steps": 180, "total_steps": 348, "loss": 0.0407, "lr": 1.4187916371218739e-05, "epoch": 1.5483870967741935, "percentage": 51.72, "elapsed_time": "1:54:50", "remaining_time": "1:47:11"}
+{"current_steps": 190, "total_steps": 348, "loss": 0.0421, "lr": 1.2840910282888211e-05, "epoch": 1.6344086021505375, "percentage": 54.6, "elapsed_time": "2:01:08", "remaining_time": "1:40:44"}
+{"current_steps": 200, "total_steps": 348, "loss": 0.0401, "lr": 1.1511488166385349e-05, "epoch": 1.7204301075268817, "percentage": 57.47, "elapsed_time": "2:07:28", "remaining_time": "1:34:19"}
+{"current_steps": 210, "total_steps": 348, "loss": 0.0438, "lr": 1.0210477047960303e-05, "epoch": 1.8064516129032258, "percentage": 60.34, "elapsed_time": "2:13:53", "remaining_time": "1:27:58"}
+{"current_steps": 220, "total_steps": 348, "loss": 0.0444, "lr": 8.948472570152874e-06, "epoch": 1.89247311827957, "percentage": 63.22, "elapsed_time": "2:20:16", "remaining_time": "1:21:36"}
+{"current_steps": 230, "total_steps": 348, "loss": 0.041, "lr": 7.735752699185711e-06, "epoch": 1.978494623655914, "percentage": 66.09, "elapsed_time": "2:26:37", "remaining_time": "1:15:13"}
+{"current_steps": 240, "total_steps": 348, "loss": 0.0317, "lr": 6.582194019564266e-06, "epoch": 2.064516129032258, "percentage": 68.97, "elapsed_time": "2:32:54", "remaining_time": "1:08:48"}
+{"current_steps": 250, "total_steps": 348, "loss": 0.0357, "lr": 5.497191297593647e-06, "epoch": 2.150537634408602, "percentage": 71.84, "elapsed_time": "2:39:17", "remaining_time": "1:02:26"}
+{"current_steps": 260, "total_steps": 348, "loss": 0.0386, "lr": 4.4895809688998655e-06, "epoch": 2.236559139784946, "percentage": 74.71, "elapsed_time": "2:45:44", "remaining_time": "0:56:05"}
+{"current_steps": 270, "total_steps": 348, "loss": 0.0289, "lr": 3.567569173085455e-06, "epoch": 2.3225806451612905, "percentage": 77.59, "elapsed_time": "2:52:02", "remaining_time": "0:49:42"}
+{"current_steps": 280, "total_steps": 348, "loss": 0.0307, "lr": 2.7386649216166233e-06, "epoch": 2.4086021505376345, "percentage": 80.46, "elapsed_time": "2:58:35", "remaining_time": "0:43:22"}
+{"current_steps": 290, "total_steps": 348, "loss": 0.0338, "lr": 2.0096189432334194e-06, "epoch": 2.4946236559139785, "percentage": 83.33, "elapsed_time": "3:04:53", "remaining_time": "0:36:58"}
+{"current_steps": 300, "total_steps": 348, "loss": 0.0279, "lr": 1.3863687049356465e-06, "epoch": 2.5806451612903225, "percentage": 86.21, "elapsed_time": "3:11:15", "remaining_time": "0:30:36"}
+{"current_steps": 310, "total_steps": 348, "loss": 0.0321, "lr": 8.7399005630238e-07, "epoch": 2.6666666666666665, "percentage": 89.08, "elapsed_time": "3:17:36", "remaining_time": "0:24:13"}
+{"current_steps": 320, "total_steps": 348, "loss": 0.0352, "lr": 4.766558909615504e-07, "epoch": 2.752688172043011, "percentage": 91.95, "elapsed_time": "3:23:55", "remaining_time": "0:17:50"}
+{"current_steps": 330, "total_steps": 348, "loss": 0.0341, "lr": 1.9760216187710788e-07, "epoch": 2.838709677419355, "percentage": 94.83, "elapsed_time": "3:30:19", "remaining_time": "0:11:28"}
+{"current_steps": 340, "total_steps": 348, "loss": 0.0315, "lr": 3.910152723075322e-08, "epoch": 2.924731182795699, "percentage": 97.7, "elapsed_time": "3:36:38", "remaining_time": "0:05:05"}
+{"current_steps": 348, "total_steps": 348, "epoch": 2.9935483870967743, "percentage": 100.0, "elapsed_time": "3:41:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9935483870967743,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 1.3349374532699585,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.1805,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 1.0496348142623901,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.0827,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 1.1902973651885986,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.0722,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.8137356638908386,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0637,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.8646667003631592,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0646,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 1.2397544384002686,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0619,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.8160271048545837,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0588,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.8985416293144226,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.0594,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.968460738658905,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.059,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.7749939560890198,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0557,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.6407869458198547,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0493,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 1.2854279279708862,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0509,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.60258948802948,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0419,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.9239497780799866,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.042,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.7352257966995239,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0432,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.8709537386894226,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0475,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.7810623049736023,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0448,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.6514085531234741,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0407,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.8177109956741333,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0421,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.9916985630989075,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0401,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 1.0323394536972046,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0438,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.920881450176239,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0444,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 1.1360812187194824,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.041,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.8304557800292969,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0317,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.8478759527206421,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0357,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 1.0847315788269043,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0386,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.6213060617446899,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0289,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 1.0422612428665161,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0307,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 0.9629487991333008,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0338,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.7275118827819824,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0279,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9140329360961914,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0321,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 1.0714858770370483,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0352,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.843151330947876,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0341,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.6754664182662964,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0315,
+      "step": 340
+    },
+    {
+      "epoch": 2.9935483870967743,
+      "step": 348,
+      "total_flos": 2.2441603085736346e+17,
+      "train_loss": 0.04925085334428426,
+      "train_runtime": 13305.7708,
+      "train_samples_per_second": 0.838,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2441603085736346e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6b5e03ab55c7eca1bec1843792810a25ab68a79d546ce327c2c6fad1fe4ce0
+size 5432

training_args.yaml

@@ -0,0 +1,34 @@
+cutoff_len: 2048
+dataset: treino_pt_rde
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+fp16: true
+gradient_accumulation_steps: 4
+learning_rate: 3.0e-05
+logging_steps: 10
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 3716
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.3
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-Instruct-v0.3/lora/mistral-finetuned
+packing: false
+per_device_train_batch_size: 8
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+quantization_method: bitsandbytes
+report_to: none
+save_steps: 1000
+stage: sft
+template: alpaca
+use_unsloth: true
+warmup_steps: 0